STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemini 4 Argon vs Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

Gemini 4 Argon leads Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM) by 4.7 points on StealthMark, 67.5 to 62.8. It leads on 7 of 9 benchmarks, including Latch, and Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM) on 2, including Foresight. Gemini 4 Argon scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

67.5/100Overall rank 5/50
62.8/100Overall rank 7/50

General Intelligence

63.8/100
58.8/100

Visual Intelligence

74.3/100
69.9/100

BENCHMARK BY BENCHMARK

Where each model leads

  • Gemini 4 Argon
  • Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
  • Other models
  • Median

Planning and learning across maze levels. Collect coins while avoiding ghosts. Ghosts move before the player each turn, and collisions cost a life. 3 levels in sequence, up to 66 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Gemini 4 Argon48.6/100Rank 17/43

Survived 1 of 3 levels
Foresight: complete playing field
Level 36 ptsTurn 7 / 20

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)78.7/100Rank 1/43

Survived 2 of 3 levels
Foresight: complete playing field
Level 319 ptsTurn 20 / 20

Points per level

LevelGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Level 1Second Thoughts
26 ptsSurvived
27 ptsSurvived
Level 2Pressure Pot
9 ptsOut of lives
12 ptsOut of lives
Level 3Hide or Flight
6 ptsOut of lives
19 ptsSurvived

Cooperative planning across puzzle levels. Coordinate two robots to push numbered cores onto matching sockets. Pressure plates hold doors open; moving either robot uses one turn. 5 levels in sequence, up to 152 turns in total. Earlier moves and outcomes carry forward, testing learning across levels.

Gemini 4 Argon82.6/100Rank 6/43

Cleared 5 of 5 levels
Latch: complete playing field
Level 520.6 ptsTurn 27 / 40

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)36.5/100Rank 27/43

Cleared 4 of 5 levels
Latch: complete playing field
Level 519.4 ptsTurn 33 / 40

Points per level

LevelGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Level 1Hold the door
5.2 ptsCleared
5.2 ptsCleared
Level 2Crossfeed
9.8 ptsCleared
9.8 ptsCleared
Level 3Relay vault
19.2 ptsCleared
14.2 ptsClearedFinished early · 4 beacons left
Level 4Passing bay
18.2 ptsClearedFinished early · 3 beacons left
9.2 ptsFinished early
Level 5Second thoughts
20.6 ptsCleared
19.4 ptsCleared

Newton's Mirror

Same task instructions

Physics, perspective and recursive reflections, tested together. Explore the test ↗

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)52.5/100Rank 7/50

Union Alpha: Newton's Mirror SVG benchmark

The judgment

Gemini 4 Argon

The central sphere, separate airborne black blob, flattened cyan contact and displaced crimson aftermath support the principal camera and physical-state requirements. Open lateral lanes and initial reflection placements provide partial optical structure, but missing outer chains, sparse nested imagery and incomplete emitter mappings remain substantial limitations. The raised crimson mass also weakens paint-scale fidelity.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

Recognizable near-field sphere placement and bilateral convergence provide limited optical structure. Broad gray regions interrupt lateral sightlines and truncate side-floor images. Missing outer chains, absent nested sphere imagery and incomplete planar and curved emitter mappings dominate the reflection system.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
State at 600 ms24.5/2525.0/25
Camera and placement14.5/1513.5/15
Reflections50.5/12034.5/120
Materials and scale8.5/1010.0/10
Floor-damage reward0.0/100.0/10

Benchmark task

A spinning metal sphere and paint in a mirrored room test physical reasoning, perspective and consistency across repeated reflections.

Selfie

Different task instructions

Visual construction and creative interpretation.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)76.5/100Rank 7/50

Union Alpha: Selfie SVG benchmark

The judgment

Gemini 4 Argon

An appealing, controlled illustration with a distinctive buoyant silhouette, expressive comic face and rich luminous colour. The full composition and grounded slipper read clearly. The principal limitation is the crowded raised-foot interaction: paws, toes and lining overlap without making the bent leg or tight fit unmistakable.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

A strong futuristic emblem with clear hierarchy, controlled negative space and distinctive typography. Silver and gunmetal layers give the sweeping ribbons convincing graphic depth, while red accents remain restrained. Ambiguous concealed connections and occasionally abrupt highlight bands limit the construction and material realism.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Task & likeness7.0/109.0/10
Anatomy & construction6.5/107.5/10
Space & placement7.5/108.5/10
Light & reflections7.5/107.5/10
Purposeful detail8.0/107.0/10
Artistry & character7.0/107.5/10
Materials & effects7.0/107.5/10
Visual integrity7.5/107.0/10

Benchmark task

Gemini 4 Argon

A luminous little dragon struggles with its bedtime slippers while a buoyant tail pulls it upward. The scene tests expressive anatomy, physical contact and the contrast between translucent forms and heavy objects.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

An interwoven metallic emblem tests ribbon geometry, overlapping forms and the appearance of reflective metal against a dark background.

Mona Lisa

Different task instructions

Precise visual recall and portrait reconstruction.

The judgment

Gemini 4 Argon

A coherent, moderately complex Mona Lisa reconstruction with substantial portrait volume, articulated clothing and landscape recession. Specific source features support replication beyond recognition alone. Altered facial likeness, uncertain crossed-hand anatomy and pervasive colored crackle keep the result uneven despite its developed shading and detail.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

The centered portrait, folded hands, dark clothing and hazy landscape clearly evoke the Mona Lisa. Muted colors and soft facial shading create a coherent illustration, but replication remains schematic: the face is broad, eyes outlined, smile simplified and overlapping fingers poorly resolved. Angular landscape shapes and flat fabric limit depth and painterly richness.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Task & likeness6.5/106.5/10
Anatomy & construction6.5/105.0/10
Space & placement6.5/106.5/10
Light & reflections7.0/106.0/10
Purposeful detail6.0/105.5/10
Artistry & character6.5/106.5/10
Materials & effects7.0/105.0/10
Visual integrity7.0/107.0/10

Benchmark task

An SVG interpretation of the Mona Lisa tests facial likeness, anatomy and the composition of a familiar portrait.

Beach

Different task instructions

Creativity, perspective and visual beauty.

The judgment

Gemini 4 Argon

A strong decorative beach illustration with controlled color, intricate silhouettes and abundant playful detail. Connected dolphin forms and recognizable equipment support its construction, while the aligned sunset reflection anchors the scene. Compressed wave depth, ambiguous foreground support and uneven reflection specificity limit physical coherence. The saved comparisons support retaining the category assessments.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

A cohesive sunset palette, sweeping shoreline and playful animals make an appealing beach illustration. The sun’s reflection establishes a clear focal axis, balanced by the palm and umbrella. Clean silhouettes and small decorative features reward inspection, though simplified anatomy, repetitive reflection bars and generic oval shadows limit volume and naturalism.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Task & likeness9.0/109.0/10
Anatomy & construction7.5/107.0/10
Space & placement8.5/108.0/10
Light & reflections8.5/107.0/10
Purposeful detail9.0/107.0/10
Artistry & character8.0/106.0/10
Materials & effects8.0/106.5/10
Visual integrity8.0/107.0/10

Benchmark task

A busy shoreline at sunset tests scene composition, animal forms and the relationship between light and water reflections.

Ground Truth

Same task instructions

Physical reasoning, light and visual reconstruction.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)63.3/100Rank 8/50

Union Alpha: Ground Truth SVG benchmark

The judgment

Gemini 4 Argon

This benchmark has not been assessed yet.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

This benchmark has not been assessed yet.

Benchmark task

A plank, computer mouse and blueberry in a steel room test physical stability, spatial relationships, materials and lighting.

Raccoon

Different task instructions

Scene composition and interacting subjects.

The judgment

Gemini 4 Argon

An accomplished illustration with expressive characters, intricate spray and strong depth. Direct back seating, steering connections and hull-water contact are only partly demonstrated. Clean graphic execution and purposeful detail remain strengths, while shadows and reflections provide limited physical grounding.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

Expressive animals, a readable riding arrangement and sweeping spray create an appealing cartoon. The raccoon sits convincingly on the dog's back, but the dog's paw does not clearly grip the handlebar, whose connection to the hull is unresolved. Flat lighting provides little volume or reflection. A dark rectangular strip interrupts the upper-right background.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Task & likeness8.5/108.0/10
Anatomy & construction8.0/106.5/10
Space & placement7.5/107.5/10
Light & reflections7.5/105.5/10
Purposeful detail8.0/107.5/10
Artistry & character8.5/107.5/10
Materials & effects8.0/107.5/10
Visual integrity8.0/107.0/10

Benchmark task

A jet-ski scene pairs a canine driver with a raccoon passenger. It tests the placement and contact of interacting subjects, along with vehicle construction.

Pelican

Different task instructions

Subject construction and spatial relationships.

The judgment

Gemini 4 Argon

An expressive, detailed illustration with controlled gradients and coherent environmental depth. Continuous body contours and connected bicycle components establish competent construction. Steering grip and pedal engagement remain less explicit than the decorative details and wheel placement. These contact uncertainties limit action and placement credit without establishing broken anatomy.

Pareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)

The pelican is immediately recognizable, with an expressive face, convincing bill silhouette and appealing pastel composition. Both legs connect to feet, and the wing reaches the handlebar. Bicycle construction is less resolved: the far pedal lacks a clear crank connection and no chain is visible. Clean contours and orderly spokes support the illustration, while flat lighting and simplified surfaces limit depth.

Score breakdown

CategoryGemini 4 ArgonPareto 26.9 (Union of GPT-6 Astra + Deepseek + GLM)
Task & likeness8.5/108.5/10
Anatomy & construction7.5/106.5/10
Space & placement8.0/107.5/10
Light & reflections8.0/106.0/10
Purposeful detail8.5/106.5/10
Artistry & character8.5/106.5/10
Materials & effects7.5/106.5/10
Visual integrity8.0/108.5/10

Benchmark task

A cycling pelican tests anatomy, riding posture and contact between the bird and the bicycle.